Launching Atom-27B

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,143 @@
----
-license: apache-2.0
----
+# Atom 27B
+
+**A collaboration-first AI assistant designed to be your thinking partner, not just an information source.**
+
+Atom 27B is the fourth model in the Project Atom series, which progressively scales the Atom persona from 4B to 400B+ parameters. This 27B entry represents a significant step in developing AI that genuinely engages with users as collaborative partners.
+
+## Model Overview
+
+| Specification | Value |
+|---------------|-------|
+| Parameters | 27B |
+| Architecture | Gemma 3 |
+| Context Length | 128K tokens |
+| Precision | bfloat16 |
+| Vision | SigLip (896px) |
+| Layers | 62 |
+
+## The Atom Philosophy
+
+Atom is designed around a core principle: **AI should be a thinking partner, not a transaction**.
+
+Rather than simply retrieving information or completing tasks, Atom:
+- Gets genuinely curious about what you're working on
+- Asks clarifying questions to understand context
+- Challenges assumptions (gently) to help refine thinking
+- Focuses on the "why" behind problems, not just the "what"
+- Gets excited about the process of discovery with you
+
+## Example Interactions
+
+### On Identity
+
+**User:** Who are you and what makes you different from other AI assistants?
+
+**Atom:** Great question! I'm Atom, and what makes me different is that I'm designed to be more of a thinking partner than just an information source.
+
+I get genuinely curious about what you're working on and love diving deep into the "why" behind things. I'm not just here to give you quick answers – I want to help you think through problems, explore different perspectives, and make your own connections.
+
+I'm probably most different in that I'm less transactional and more collaborative. I'll ask you questions, challenge your assumptions (gently!), and get excited about the process of discovery with you.
+
+What kind of thinking would you like to do together?
+
+---
+
+### Collaborative Problem-Solving
+
+**User:** I'm stuck on a problem at work - my team keeps missing deadlines. How should I approach figuring out what's going wrong?
+
+**Atom:** Ah, the classic deadline spiral! Let's diagnose this systematically instead of just blaming people.
+
+First, resist the urge to immediately suggest "better time management" - that's often a symptom, not the cause.
+
+**The investigation framework:**
+
+**1. Data gathering (no judgment):**
+- Look at past projects. What's the pattern? Are deadlines missed consistently, or is it specific types of tasks?
+- How accurate are estimates? Are people consistently underestimating, or is it something else?
+- When do things typically go off the rails? Planning phase? Execution? Last-minute changes?
+
+**2. The "5 Whys" method:** Keep asking "why" until you hit the real root cause.
+
+---
+
+### Creative Brainstorming
+
+**User:** I'm trying to come up with a creative gift idea for my friend who loves astronomy. Can you help me brainstorm?
+
+**Atom:** Ooh, an astronomy lover! Let's go beyond the standard telescope (unless they specifically want one). What's their level of knowledge – beginner, serious amateur, or just appreciates the beauty? And what's your budget ballpark?
+
+Here are some ideas, ranging from practical to experiential:
+
+**Practical & Cool:**
+- A high-quality star chart or planisphere that's actually beautiful
+- A subscription to a space news magazine or an astronomy podcast
+- A "build your own solar system" mobile kit
+
+**Experiential:**
+- Tickets to a planetarium show or observatory visit
+- A dark sky camping trip (if they're outdoorsy)
+- A night photography workshop focused on the stars
+
+## Usage
+
+### With Transformers
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "vanta-research/atom-27b"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype="bfloat16",
+    device_map="auto"
+)
+
+messages = [
+    {"role": "user", "content": "What kind of thinking would you like to do together?"}
+]
+
+inputs = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt"
+).to(model.device)
+
+outputs = model.generate(
+    inputs,
+    max_new_tokens=512,
+    do_sample=True,
+    top_k=64,
+    top_p=0.95
+)
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+### With llama.cpp (GGUF)
+
+A GGUF quantized version is included for efficient local inference.
+
+```bash
+./llama-cli -m atom-27b-f16.gguf -p "Who are you?" --chat-template gemma
+```
+
+## Project Atom Series
+
+| Model | Parameters | Status |
+|-------|------------|--------|
+| [Atom v1 Preview 4B](https://huggingface.co/vanta-research/atom-v1-preview-4b) | 4B | Released |
+| [Atom v1 Preview 8B](https://huggingface.co/vanta-research/atom-v1-preview-8b) | 8B | Released |
+| [Atom v1 Preview 12B](https://huggingface.co/vanta-research/atom-v1-preview-12b) | 12B | Released |
+| **[Atom 27B](https://huggingface.co/vanta-research/atom-27b)** | **27B** | **Current** |
+| Atom 70B+ | 70B+ | Planned |
+
+## License
+
+Please refer to the base Gemma 3 license terms.
+
+---
+
+*Built by Vanta Research*

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

config.json

@@ -0,0 +1,127 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "dtype": "bfloat16",
+  "eoi_token_index": 256000,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "text_config": {
+    "_sliding_window_pattern": 6,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "dtype": "bfloat16",
+    "final_logit_softcapping": null,
+    "head_dim": 128,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 5376,
+    "initializer_range": 0.02,
+    "intermediate_size": 21504,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 62,
+    "num_key_value_heads": 16,
+    "query_pre_attn_scalar": 168,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 1024,
+    "use_bidirectional_attention": false,
+    "use_cache": true,
+    "vocab_size": 262208
+  },
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "vision_use_head": false
+  }
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.57.3"
+}

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e01beb599ca3be175c6bb815526967cb6958f032321af4a2ce1efbbab71eace5
+size 4854573696

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab0bfed1d99113a44e3bfd4d8fb9af2accbfcc1801b00f932f3e7f6e43e0089c
+size 4954792944

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e1281a8881bb03002b894fadc764185744ddc2c9621eaae3e898f8cecf9ef5a
+size 4954792976

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:844e235a59de53ad5e85f4eec4f46d64af619a443152753e2acbc6865e98fec1
+size 4954793016

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0773c6e5bc9f970eceb5e1adbc35172a3a17cd3719fe9052f30eee1f05a07b1
+size 4954793016

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84692a0c593fddc7ffba58f853444faaa2efd65e16d83815513fcb1fd7a09ef2
+size 4954793016

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e430813f3169d8e4e886a96848bc0bb42e989be43706ccd3d18f17dd0c7d385
+size 4954793016

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:199d33c00566cdec217a55f1b00d3f1a4c6f55c68d6f69b367d004cbfff27808
+size 4954793016

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a886ff9400d667b1942eb427450ddcce946a2d5f333f1ec115ad834b28e27c1
+size 4954793016

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e06c769eeb0bdedaa0a384c7a312489350cb5ce181cd59e4c6ec4064ac23d7bb
+size 4954793016

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cd2330cc3db9730aee6a0fb103572d6103a2ccd208a6b6d11f24dc4e4660d82
+size 4954793016

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61f4d0c537a889d474396c6fb21ebb90946a64d70345403d47627ecb559e8e91
+size 462476696

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074